© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18876
    Prev
    Next
    INDEX
    Explanations

    symbols or formatting related to data or code configurations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ...
    -0.54
     Golden
    -0.52
    /");
    -0.50
    <?
    -0.50
     ed
    -0.49
    ansky
    -0.48
    }}_{\
    -0.48
    stalline
    -0.48
     ...
    -0.48
    ="<?
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    enderror
    0.77
     fallu
    0.76
     désolés
    0.71
    पया
    0.70
    +#+#
    0.69
    AddTagHelper
    0.69
     stället
    0.66
     tombé
    0.66
     InputDecoration
    0.65
    Activations Density 0.042%

    No Known Activations